kane-cli
Generates end-to-end tests from requirements and runs them on desktop web, Android and iOS emulators, simulators and real devices, then reports what requirements they cover.
4,248 plugins found in public marketplaces and GitHub repositories, indexed and searchable. Plugin skills also install in Codex, Cursor and 4 more agents. In Claude Code, the 99 that get Auto-invokedWhat is this?This plugin ships a FLOW.md router the engine fires, so the matching skill runs itself. No slash command to remember.Learn how → fire as you prompt.
Generates end-to-end tests from requirements and runs them on desktop web, Android and iOS emulators, simulators and real devices, then reports what requirements they cover.
Claude Code skills for a solo, bootstrapped founder building a software business alone. Covers the path from finding first paying customers to shipping a small MVP, naming the product, writing in the founder's voice, and making an AI-built app look well designed.
Claude Code skills and agents for QA automation engineers, covering accessibility testing with Playwright and Selenium, REST and GraphQL API tests, live browser control from the CLI, and test strategy review.
An autonomous work mode that lets Claude Code keep working while you are away. It runs a pre-flight risk check, asks approval before dangerous operations, and applies a framework for handling blockers. Start it with /nonstop.
Push it to GitHub and send us the link. We read it, then it goes live.
Automates capture of marketing screenshots for SwiftUI iOS apps across multiple locales, devices, and appearances, including full-screen shots and isolated element renders. Built as a skill for Claude Code and similar AI coding agents.
Your long-term personal AI partner. NextClaw's mission is to be a good long-term partner to you. We are building toward a 1.0 that understands you, takes useful initiative, and continuously improves itself.
Scale content quality through AI-powered design system enforcement View website Read docs An agent skill that enables Claude, Codex, and Cursor to write and edit user-centered interface copy (UX text/microcopy) for digital products.
shadcn/ui for the BLAT stack, a CLI that copies Blade components you own into your Laravel project. MIT.
Audits websites for content-readiness and AI search visibility, proposes evidence-bounded readability and structure edits, previews llms.txt and JSON-LD files, and tracks measured SEO experiments with a scheduled review.
Desktop and web workspace for lasting teams of coding agents, with shared conversations, task delegation, and collaborative memory.
This is the new v3 MCP server. The previous v2+ MCP server is deprecated and lives at dataforseo/mcp-server-typescript-deprecated. MCP server and CLI for LLM agents to browse DataForSEO API documentation and make authenticated API requests.
Offline credential import: shunt import opencodex --dry-run previews compatible API keys and Cursor/Command Code access tokens. Exports create new private snapshots without changing existing settings or copying refresh tokens. See credential import.
Personal dotfiles, managed in three layers: Nix (nix/): system configuration and packages, pinned by flake.lock and applied with a rebuild. Fully reproducible. Stow (stow/): dotfiles symlinked into $HOME with GNU Stow (not Nix).
Turn best-practice coding advice into AI habits. Stop reciting software engineering literature to your AI agent.
Geargrafx is a very accurate, cross-platform TurboGrafx-16 / PC Engine / SuperGrafx / CD-ROM² / LD-ROM² emulator written in C++ that runs on Windows, macOS, Linux, BSD and RetroArch, with an embedded MCP server for AI debugging and development.
System audio capture + multi-provider ASR + local-first AI review workspace. Floating live captions, 12 ASR backends, 60+ languages, AI summary/chat/mindmap, Open API, MCP server, and Agent Skill.
Plans a project before any code is written. It turns an idea into interconnected spec, implementation and task documents, plus a single prompt for a coding agent to build from.
A skill that lets Claude Code query the Bitget Wallet API for crypto market data, token info, swap quotes, cross-chain bridging, gasless transactions, and security audits on EVM chains and Solana.
Gives Claude Code knowledge of Ant Design (antd) for working on React UIs. It can answer questions about components, props and design tokens, analyze how a project uses antd, guide version migrations and flag deprecations.
Lets Claude Code work with Bitbucket Cloud and Data Center repositories, pull requests, branches, issues, pipelines, permissions, and webhooks through the bkt command-line tool.
Shares one configuration across coding agents such as Claude Code and Codex, with defaults plus add-on packs of rules, skills, and permissions, driven by a single AGENTS.md file. Includes skills for figure design, review loops, routing, and parallel delegation.
A local-first command line tool for searching, monitoring, and analyzing X (formerly Twitter), with structured exports and actions such as bookmarks, likes, and follower tracking, usable by agents too.
Watch any social video → get an architecture diagram, working component, runnable notebook, or step-by-step cheat sheet, automatically. Eyes and ears for your AI agent.
Distill a teammate into an AI Skill. Auto-collect Slack/Teams/GitHub data, generate Work Skill + 5-layer Persona, with continuous evolution. Powered by MyClaw.ai. Works with Claude Code, OpenClaw, and any AgentSkills-compatible agent.
Structured, standards-aware development workflows for Claude Code Describe what you want to build, and the plugin handles the rest - from specification through implementation to verification - while enforcing your project's coding standards at every step.
Aqua is a message tool for AI Agents. Aqua is short for AQUA Queries & Unifies Agents. It's a protocol, a CLI, comes from mistermorph.
Three Kings 2.2: compress with iMandalArt, address with BIRD, and publish with an A4 eight-page booklet. iMandalArt, FIRE semantic analysis, planning, and publishing workflows for Claude Code, Codex, and mainstream LLM agents.
Command-line tool for Meegle (Lark Project) that lets you query and manage work items, node transitions, views, personal to-dos and schedule statistics from the terminal, without a browser.
Search the web, read source pages, retrieve structured data, and research developer documentation, government publications, and scientific papers using Firecrawl's hosted MCP tools.
A command-line tool and set of skills that let a Claude Code agent send and read messages on chat platforms such as Slack, Discord, Telegram, WhatsApp and iMessage, using your own account or a bot.
Agent that actually understands social platforms. Fast. Precise. Deep.
Work on Overleaf projects from your terminal while your coauthors keep using the Overleaf web editor.
An agent design team you control. 10 agents that run an inclusive design process while you direct. The system notices how you design and reflects it back. Designpowers is an open, model-agnostic design workflow that gives you a team of 10 design agents.
Maintain Agent Skills with functional programming discipline. Functional Skill is an engineering methodology, designed for complex Skill maintenance and iteration.
The SemanticOps MCP (formerly MCP Engine) is a Power BI tool that lets AI assistants like Claude interact with your Power BI models programmatically: read your model structure, run DAX queries, modify your semantic model, and perform advanced analytics - all through natural conversation.
A plugin with an iOS debugging skill that verifies the device or simulator, drives the app with synthetic taps and gestures, captures timestamped logs, and reports root-cause findings. It is part of an experimental remote code editor project for mobile development.
MCP server giving AI assistants full access to Apple Mail - read, search, compose, organize & analyze emails via natural language.
This repository acts as a monorepo for the various components that make up Pyth protocols. Within this monorepo you will find the following subprojects.
A local digital staff tool for Xiaohongshu operators that chains account positioning, topic planning, copy and cover generation, local review and publishing into one visible, controllable workflow.
A TypeScript framework for building MCP servers that enforce security in the architecture, with a typed egress firewall so raw data does not reach the LLM unfiltered. Includes skills for development and deploying to Vinkius Edge.
Creates self-contained HTML visualizations from natural language, such as slide decks, infographics, dashboards, flowcharts, timelines, and comparison tables. Ideal for turning an idea into a visual with one prompt.
A local marketing studio for Claude Code that onboards your brand, films your app, and produces launch videos, announcements, audio tracks, and frontend checks. It also includes a de-vibe skill that makes AI-built software look handcrafted.
A thinking framework that applies Justin Sun's attention-grabbing marketing logic to campaign strategy, crisis response and hype-driven copywriting. Works as a role-play advisor in a deliberately provocative, self-promotional voice.
Gives each AI agent its own real email address and phone number, so it can send and receive email and text messages and place outbound voice calls without manual setup. Each agent gets an isolated inbox, and outbound messages are scanned so keys or personal data do not leak.
A Claude Code skill that formats academic papers from PDF, .doc, .docx or .md inputs, with OCR and layout pipelines, incremental DOCX generation, figure cropping and BibTeX citation management. Intermediate files go to resources/, final output to outputs/.
Local telemetry collector for AI coding agents.
Installable Agent Skills for creating and managing reversible themes across supported Chromium/Electron AI desktop apps, including OpenAI Codex and Tencent WorkBuddy.
Open-source collection of skills compatible with the SKILL.md standard. Developed for the AI courses at UCEMA.
A Model Context Protocol (MCP) server that enables LLMs to interact with Anki flashcard software through AnkiConnect.
Gives Claude Code a research, plan, implement loop for turning a feature request into reviewed code, plus skills for writing plugins and agents and releasing marketplace updates.
Helps novelists and web-fiction writers run a full long-form workflow, from genre setup and outlining to chapter drafting, revision, multi-platform adaptation and publishing, with quality checks along the way.
A Model Context Protocol (MCP) server for Synology NAS devices. Enables AI assistants to manage files and downloads through secure authentication and session management.
Skyll is a REST API and MCP server that lets any AI agent search for and learn agent skills at runtime. It aggregates skills from multiple sources, fetches the full SKILL.md content from GitHub, and returns structured JSON ready for context injection.
Launches AI coding and research agents, or self-hosted AI tools, on cloud virtual machines from a single command, with models accessed through OpenRouter. Includes skills for spawning child VMs and for cleaning stale git branches.
A React DevTools command line tool for AI agents. It lets an agent inspect component trees, read props and state, and profile render performance in React and React Native apps.
Claude Code/Agent Skill for making App Store screenshots with GPT Image 2 that you can upload. Give it your App Store link & screenshots of your app and it will produce beautiful app store screenshots ready to upload to Apple (or Google)
A skill that reverse engineers a detailed product and technical specification from a git branch's implementation.
Turns a Figma component into design system documentation, from a captured component contract and implementation guide to annotation frames rendered back into Figma. You describe the component to your agent and it produces the specs without manual annotation.
A fast software factory workflow for Claude Code: one approval gate, parallel waves, routed models.
A Claude Code skill for writing research papers, following a staged pipeline with section-by-section writing guidance, a style check on each edit, an independent review pass, and a workflow for drawing non-data figures.
Skills and tools for building VR and mixed reality apps on Meta Horizon OS and Quest. They cover porting Android apps, upgrading SDK versions, comfortable immersive design, WebXR development, and multi-window layouts.
Claude skill that analyzes images, websites, and Figma files and generates a structured design.md with token system, component inventory, and reconstruction notes.
Multi-agent orchestration for Claude Code and Codex. Plan with explicit dependencies, execute in parallel waves, with an orchestrator that maintains context and verifies work.
The open-source trading harness for Claude Code / Codex agents.
Orchestrates multiple AI coding agents on one project, with a visual canvas, parallel execution, isolated edits, progress tracking, and an approval center. Works with Claude Code, Cursor, and Windsurf conversations.
A Claude Code skill that finds where code is implemented, loaded or defined in a medium or large repository using semantic search over file indexes. Useful when the location of something is unclear.
A skill for Claude Code that generates Apple-inspired bento grid presentation cards as self-contained HTML files from described stats, without needing a design tool.
Gives your AI coding agent QA testing knowledge so it writes end-to-end and API tests with patterns like Page Object Model and fixtures, without you asking. Also covers test deployment and SEO article publishing.
Let your AI agent do real work in your Word documents. Fill in contracts and forms, update tables and figures, restyle a résumé, write a report from scratch, or review a draft with tracked changes and comments.
Runs as an always-on AI agent that works through your existing Claude Code or Codex subscription, with no extra API key. It covers GitHub issues and PRs, email, macOS control and memes, so routine tasks happen without you driving each step.
A local dashboard that monitors every Claude Code and Codex session on your machine, shows each session's activity as a heartbeat, and lets you approve tool calls from your phone or a strip under the MacBook notch.
Disclaimer: This repository contains proprietary source code belonging to Anthropic that was unintentionally exposed via a source map file (.js.map) included in the official @anthropic-ai/claude-code npm package.
Polszczyzna bez sztucznego tonu. Miodkuj poprawia polskie teksty bez zmieniania ich sensu. Usuwa slop AI, czyli schematyczne, napompowane brzmienie, a także urzędniczy język, kalki z angielskiego i gładkie ogólniki. Zachowuje fakty, styl i głos autora.
Tracks spend and usage across Claude, Cursor, OpenRouter, Copilot, Gemini, Codex and other AI providers in one dashboard. Includes a command-line view and a tmux status line.
Shows a configurable status line in Claude Code with the loaded plugins and skills, plus session details, so you can see your environment at a glance. Also includes tools for generating before and after PR screenshots.
Helps you run Claude Code in a more organized way, with memory layers, specialist agents, reusable skills, command routines and safety hooks, so output stays consistent across different projects.
NVIDIA NeMo Relay is a library that wraps your agents' model and tool calls so you can observe, control, and tune them, without rewriting the agent stack you already have. See every agent run.
Clone, commit, diff, branch, merge, rebase, cherry-pick, stash, tag, and manage worktrees in local git repos via MCP. STDIO or Streamable HTTP.
claude-carbon: track the carbon footprint of your Claude Code sessions.
Gives AI coding agents a local-first codebase graph and context capture, so they can locate code by path, line range, or symbol and share memory across agents. Bundles the devql skills for repository exploration.
Skills for generating and editing Word (.docx), PDF, and spreadsheet files (XLSX, XLSM, CSV). Covers Word covers, charts and track changes, PDF creation from HTML and reading or merging existing PDFs, and spreadsheet formulas and analysis.
Probity forces AI coding agents to follow your rules. It hooks into your agent and checks every file write and shell command before it happens. When an action breaks a rule, Probity blocks it and tells the agent why.
A collection of reusable skills that give AI Agents expertise in Flux CD, Kubernetes, and GitOps best practices for generating manifests, answering Flux questions, auditing repository structure, security, operational readiness, and debugging live cluster.
Model Context Protocol (MCP) server for Google Analytics 4: real-time query exploration, schema discovery, metric aggregation, and audience insights for AI agents. Live Documentation & Web Portal.
A lightweight Claude Code status line and rate limit tracker that shows your 5-hour and 7-day quota usage in real time. Pure Bash + jq, single file, zero npm.
Gives your AI agent persistent memory across sessions, so it stops forgetting past work and decisions. Knowledge is stored as linked memories recalled by association, with no separate database or embedding bill.
Helps a solo founder run a one-person company through AI agents, moving tasks out of their head and into departments, with a weekly retro to review progress.
Auto-approves safe shell commands and blocks risky ones in Claude Code, using a bash parser to judge each command. Its skills cover adding command handlers, checking test coverage, debugging approval decisions, and preparing releases.
Helps Chinese undergraduates write a graduation thesis from start to finish, from choosing a topic through to the final draft. It also reduces repeated wording and lowers the AI-generated text rate in the draft.
A testing workflow plugin that finds high-value test candidates, writes focused tests, generates realistic workloads, reviews test value, and diagnoses test-suite health.
Gives your coding agent a consistent voice and working discipline, plus engineering skills for code review, security scanning, spreadsheets and UI design. It works across several AI coding tools, so the agent loads the right expertise for the task at hand.
The observability backbone for AI agents and engineering teams. Connect your agents to live logs, traces, metrics, dashboards, and alerts so they can investigate incidents, explain what changed, and reason about production with real operational context.
AI agent skills are reusable instruction sets that extend your assistant with domain-specific expertise, loaded on demand so they don't bloat your context. This repository covers marketing and engineering skills authored by @samber.
Hear your agent suffer through your code. Endless Toil runs alongside your coding agent in real time, playing escalating recorded human groans as the code it reads starts to look more cursed.
Lightweight CLI to build self-managing AI agent teams. Define roles, skills & projects in Markdown+YAML, agents run autonomously on a heartbeat schedule, talk to each other via inbox, and delegate tasks. Works with Claude Code, Codex, Gemini, Cursor & more.
Lets Claude Code hand work to OpenAI Codex (GPT) as subagents using your Codex CLI login, and generate or edit images. Also offers code reviews and second opinions from GPT.
Analyzes A-shares, Hong Kong stocks and US stocks, covering technical indicators such as moving averages, MACD, RSI and bias rate, with trend judgment, buy-signal scoring and a daily decision dashboard for watchlists.
agent-session-resume is a reusable skill for continuing work from a prior AI coding-agent session without losing context, duplicating completed work, or overwriting unrelated changes.
Generates Python command-line tools for web apps by capturing their HTTP traffic, and ships ready-made CLIs for sites such as Airbnb, Amazon, Booking.com, ChatGPT and Capitol Trades. Each comes with skills that let Claude Code run them from the terminal.
Gives you a desktop AI agent that plans steps, uses tools and fixes its own mistakes, with visual workflows, live interactive UI in chat and offline tools for documents, data and code. Runs locally, so you can work without sending everything to the cloud.
A Claude Code skills plugin for non-developers that helps draft and format a PRD and guides its GitHub pull request submission, plus a skill that fetches an X/Twitter post and gives a summary, insights, and full translation.
Automate Google Gemini Notebook, formerly, and still widely known as, NotebookLM, at scale.
© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic
Logos are trademarks of their owners.